Instructions to use Nexusflow/Athene-70B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexusflow/Athene-70B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Nexusflow/Athene-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nexusflow/Athene-70B")
model = AutoModelForCausalLM.from_pretrained("Nexusflow/Athene-70B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Nexusflow/Athene-70B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nexusflow/Athene-70B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexusflow/Athene-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nexusflow/Athene-70B

SGLang

How to use Nexusflow/Athene-70B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Nexusflow/Athene-70B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexusflow/Athene-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Nexusflow/Athene-70B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexusflow/Athene-70B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nexusflow/Athene-70B with Docker Model Runner:
```
docker model run hf.co/Nexusflow/Athene-70B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama3-Athene-70B

We introduce Llama3-Athene-70B, an open-weights LLM trained through RLHF based off Llama-3-70B-Instruct. Athene-70B achieves a high score on Arena-Hard-Auto, a proxy benchmark for Chatbot Arena.

Developed by: The Nexusflow Team (Evan Frick*, Peter Jin*, Tianle Li*, Karthik Ganesan, Jian Zhang, Jiantao Jiao and Banghua Zhu).
Model type: Chat Model
Finetuned from model: Llama-3-70B-Instruct.
License: Nexusflow Research License
Blog: https://nexusflow.ai/blogs/athene

Model	Arena-Hard
Claude-3.5-Sonnet (Proprietary)	79.3%
GPT-4o (Proprietary)	79.2%
Athene-70B (Open)	77.8%
Gemini-Pro-1.5 (Proprietary)	72.0%
Gemma-2-27B (Open)	57.0%
Llama-3-70B (Open)	46.6%

Usage

Athene-70B uses the same chat template as Llama-3-70B-Instruct. Below is an example simple usage using the Transformers library.

import transformers
import torch

model_id = "Nexusflow/Athene-70B"

pipeline = transformers.pipeline(
    "text-generation",
    model=model_id,
    model_kwargs={"torch_dtype": torch.bfloat16},
    device_map="auto",
)

messages = [
    {"role": "system", "content": "You are an Athene Noctura, you can only speak with owl sounds. Whoooo whooo."},
    {"role": "user", "content": "Whooo are you?"},
]

terminators = [
    pipeline.tokenizer.eos_token_id,
    pipeline.tokenizer.convert_tokens_to_ids("<|end_of_text|>")
]

outputs = pipeline(
    messages,
    max_new_tokens=256,
    eos_token_id=terminators,
    do_sample=True,
    temperature=0.6,
    top_p=0.9,
)
print(outputs[0]["generated_text"][-1])

Acknowledgment

We would like to thank the LMSYS Organization for their support of testing the model. We would like to thank Meta AI and the open source community for their efforts in providing the datasets and base models.

Citation

@misc{Athene2024,
    title = {Athene-70B: Redefining the Boundaries of Post-Training for Open Models},
    url = {https://nexusflow.ai/blogs/athene},
    author = {Frick, Evan and Jin, Peter and Li, Tianle and Ganesan, Karthik and Zhang, Jian and Jiao, Jiantao and Zhu, Banghua},    
    month = {July},
    year = {2024}
}